next

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses key behaviors: does not enter functions, the effect of the 'instruction' flag (step over machine instruction), and the count parameter for multiple steps. It also mentions rr replay sessions. However, it does not explicitly state that the tool modifies the debug session state (e.g., advancing the program counter), but this is implied and typical for a stepping tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded with the main purpose. Parameter descriptions are listed with clear formatting. Every sentence adds value without unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that the tool has an output schema (not shown but indicated) and the parameters are described, the description is complete enough. It covers the main behavior, parameter effects, and sibling differentiation. No missing critical information.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description explains the 'count' and 'instruction' parameters with their defaults and meanings, which is helpful since the schema has 0% description coverage. The 'session_id' parameter is not described, but its purpose is clear from context (identifying the debug session). The description adds value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool steps forward over the next source line or machine instruction without entering called functions. It distinguishes from sibling tools 'step' and 'reverse-next' by explicitly advising use of 'step' to enter calls and 'reverse-next' for stepping backwards.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit when-to-use guidance: step without entering functions. It also tells when to use alternatives: 'Use step to enter calls instead' and 'use reverse-next to step backwards' for rr sessions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.